RCI: A Score for Evaluating Global and Local Reasoning in Multimodal Benchmarks
机构 * Oracle AI
Comments Accepted in EMNLP 2025
期刊&会议
EMNLP
Conference on Empirical Methods in Natural Language Processing · 会议 · Natural Language Processing
Drift-Adapter: A Practical Approach to Near Zero-Downtime Embedding Model Upgrades in Vector Databases
机构 * Rutgers University - New Brunswick（新布朗斯维尔罗切斯特大学）
Comments EMNLP 2025 Main 12 pages, 6 figures
Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine Translation
机构 * Institute for Language, Cognition and Computation（语言、认知与计算研究所） ； School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
Comments EMNLP 2025
Fin-ExBERT: User Intent based Text Extraction in Financial Context using Graph-Augmented BERT and trainable Plugin
机构 * Fidelity Investments（fidelity投资公司）
Comments 10 pages, 5 figures, accepted at EMNLP 2025 Industry Track
Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models
Comments EMNLP 2025 (Main Conference)
How to Make Large Language Models Generate 100% Valid Molecules?
机构 * Nanyang Technological University（南洋理工大学） ； HKUST(GZ)（香港科技大学（广州）） ； HKUST（香港科技大学） ； NUS（国立新加坡大学） ； UCAS（中国科学院大学） ； UCLA（加州大学洛杉矶分校） ； Hunan University（湖南大学） ； UC Merced（加州大学默塞德分校）
Comments EMNLP 2025 Main
The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models
机构 * Department of Statistics, LMU Munich（统计系，慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； CISPA Helmholtz Center for Information Security（信息安全赫尔姆霍兹研究中心）
Comments Accepted at the 2nd UncertaiNLP Workshop @ EMNLP 2025
Emergent morpho-phonological representations in self-supervised speech models
机构 * Department of Neurological Surgery, University of California, San Francisco（加州大学旧金山分校神经外科系） ； Department of Linguistics, University of Southern California（南加州大学语言学系） ； Center for Computational Language Sciences, University of Southern California（南加州大学计算语言科学中心）
Comments Accepted at EMNLP 2025
LLMs Behind the Scenes: Enabling Narrative Scene Illustration
机构 * Midjourney ； Northwestern University（西北大学） ； University of California, Santa Cruz（加州大学圣克鲁兹分校）
Comments Accepted at EMNLP 2025
TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant?
Comments Accepted to EMNLP 2025 Findings
RAR$^2$: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval
机构 * Department of Computing, The Hong Kong Polytechnic University（计算机系，香港理工大学） ； Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology（可信自主系统研究院和计算机科学与工程系，南方科技大学）
Comments Accepted by EMNLP 2025 Findings
On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Concepts
机构 * MIT CSAIL（麻省理工学院计算机科学与人工智能实验室） ； MIT BCS（麻省理工学院脑科学与认知研究中心）
Comments EMNLP 2025 (Main)
Speculative Safety-Aware Decoding
机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, CAS（人工智能安全国家重点实验室，计算技术研究所，中国科学院） ； School of Computer Science & Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学）
Comments Camera-ready version of EMNLP 2025 main conference. Code: https://github.com/k-k1w-w1x-x/Speculative-Safety-Aware-Decoding
LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators
机构 * GovTech, Singapore（新加坡政府科技局） ； Singapore University of Technology and Design（新加坡科技设计大学）
Comments EMNLP 2025 System Demonstration Track
Probabilistic Soundness Guarantees in LLM Reasoning Chains
机构 * University of Pennsylvania（宾夕法尼亚大学） ； University of Texas at Austin（德克萨斯大学奥斯汀分校）
Comments EMNLP 2025 camera ready
PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process
机构 * Computer Science and Engineering, University of Michigan, Ann Arbor, MI（计算机科学与工程系，密歇根大学，安娜堡分校） ； Department of Political Science, Northeastern University, Boston, MA（政治学系，东北大学，波士顿分校）
Comments EMNLP'25 Main
Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking
机构 * Princeton Language and Intelligence, Princeton University（普林斯顿语言与智能研究所，普林斯顿大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Comments EMNLP 2025; Code at https://github.com/princeton-pli/QRHead
Improving LLM Reasoning through Interpretable Role-Playing Steering
机构 * Center for Information and Language Processing, LMU Munich（信息与语言处理中心，慕尼黑大学） ； Northwestern University（西北大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML）） ； New Jersey Institute of Technology（新泽西理工学院）
Comments Accepted at EMNLP 2025 Findings
Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation
机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Shenzhen Research Institute of Big Data（深圳大数据研究院） ； Chengdu Technological University（成都理工大学） ； University of Copenhagen（哥本哈根大学）
Comments Cultural Analysis, Cultural Visual Understanding, Cultural Image Transcreation. Accepted by EMNLP 2025 (Oral)
TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents
机构 * Yonsei University（延世大学）
Comments EMNLP 2025 Findings
BRIT: Bidirectional Retrieval over Unified Image-Text Graph
机构 * Fujitsu Research India（富士通印度研究）
Comments Accepted in EMNLP-2025 Findings
ToDi: Token-wise Distillation via Fine-Grained Divergence Control
Comments EMNLP 2025 (Oral)
No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discovery
机构 * Stevens Institute of Technology（史蒂文斯理工学院）
Comments EMNLP 2025
Multilingual Prompting for Improving LLM Generation Diversity
机构 * New York University（纽约大学） ； Columbia University（哥伦比亚大学）
Comments Accepted by EMNLP 2025
Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； The Hong Kong University of Science and Technology（香港科技大学） ； Southeast University（东南大学）
Comments EMNLP 2025 Main
Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments
机构 * Department of Computer Science, Iowa State University（计算机科学系，爱荷华州立大学） ； Department of Civil, Construction and Environmental Engineering, Iowa State University（土木、建设与环境工程系，爱荷华州立大学）
Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains
机构 * Department of Computer Science, Iowa State University, Ames, IA, USA（计算机科学系，爱荷华州立大学） ； Department of Civil, Construction and Environmental Engineering, Iowa State University, Ames, IA, USA（土木、建设与环境工程系，爱荷华州立大学）
Journal ref Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation
机构 * University of Edinburgh（爱丁堡大学） ； Sword Health ； Queen’s University Belfast（贝尔法斯特女王大学）
Comments Accepted to EMNLP 2025 (Findings)
Audio-centric Video Understanding Benchmark without Text Shortcut
机构 * Tsinghua University（清华大学） ； University of Cambridge（剑桥大学） ； ByteDance（字节跳动）
Comments Accepted for publication in the Proceedings of EMNLP 2025 (Main Conference)
UltraIF: Advancing Instruction Following from the Wild
Comments Accepted by EMNLP 2025
